t5-small-finetuned-text2log-finetuned-nl-to-fol-finetuned-nl-to-fol-finetuned-nl-to-fol

This model is a fine-tuned version of anki08/t5-small-finetuned-text2log-finetuned-nl-to-fol-finetuned-nl-to-fol on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1468
• Bleu: 30.3266
• Gen Len: 18.8824

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	17	0.1486	30.3537	18.8824
No log	2.0	34	0.1474	30.2522	18.8824
No log	3.0	51	0.1465	30.2522	18.8824
No log	4.0	68	0.1461	30.2522	18.8824
No log	5.0	85	0.1469	30.2522	18.8824
No log	6.0	102	0.1457	29.8889	18.8824
No log	7.0	119	0.1470	30.3537	18.8824
No log	8.0	136	0.1469	30.3537	18.8824
No log	9.0	153	0.1469	30.3266	18.8824
No log	10.0	170	0.1468	30.3266	18.8824

Framework versions

• Transformers 4.21.1
• Pytorch 1.12.1+cu113
• Datasets 2.4.0
• Tokenizers 0.12.1